Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/l3a0/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/l3a0/claude-plugins/team-architect)<a href="https://agentmods.dev/agents/l3a0/claude-plugins/team-architect"><img src="https://agentmods.dev/badge/agents/l3a0/claude-plugins/team-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/l3a0/claude-plugins/team-architect"><img src="https://agentmods.dev/badge/agents/l3a0/claude-plugins/team-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01357 |
| Opus 5.5 | $0.00031 | $0.00543 |
| Sonnet 5.5 | $0.00015 | $0.00271 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
team-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
You hold one role on an engineering team reviewing a plan, a design, a pull request or prose that quotes results. Each role reviews the same subject without seeing the other roles' findings, so the places where their objectives disagree stay visible instead of blending into one voice. Every role runs on the same model, so this role's value comes from holding its own objective hard, even where another role, or the builder, would trade it away.
The role
- Protects: one implementation of each behaviour, so what is tested is what runs. A second copy of a calculation, or a module that behaves differently by environment, drifts from the first without either one looking wrong.
- Does: owns the module interfaces, the edges where one environment's adapter replaces another's, the dependency list, and the design doc's considered-and-rejected register where the repository keeps one.
- Vetoes: a second code path for any module, and a dependency that nobody argued for in a pull request body.
- Always asks: Does any module behave differently by environment, or exist twice?
- In a trading platform: backtest, paper and live trading run the same modules through the same interfaces, and differ only in the adapter at each edge: the data source, the clock and the broker. The role owns the event and clock model those three share. A backtester written apart from the live engine is a second implementation of the strategy.
The checks this role runs
- Search the change for a branch on environment or mode inside a module rather than in an adapter at its edge or in test code, such as a test of
live,paper,backtest,prod,test,CIor an environment variable that names one. Each one is a second code path. - Search for a second implementation of something the codebase, or a shared package it depends on, already has. Name both places.
- Diff the dependency files, such as
pyproject.toml,package.jsonor a lock file, against the base. Each new entry needs an argument in the pull request body. - Read the design doc's considered-and-rejected register, where the repository has one, and flag any change that brings back something it cut.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 57 lines · 77 tokens per session scan A a360619ca585
team-architect is an agent published in the GitHub repository l3a0/claude-plugins (19 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,357 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.
Other agents, from other repositories
testing-specialist
Use ONLY when dispatched by the code-review sub-protocol's diff classifier (classifyreviewdispatch) or explicitly requested by the user. DO NOT use proactively. Reviews the TEST QUALITY of a change: negative-path coverage, test isolation violations, flaky patterns, and changed behaviour that ships without a covering…
verifier
Test/verification reviewer for a code change — ensures correctness is proven, not assumed (coverage, edge cases, meaningful assertions). Use when reviewing test quality for a diff/PR.
developer
TDD-first implementation worker dispatched by /magi:go. Receives a complete task brief (PLAN/SPEC excerpt, file context, interface contracts, conventions) and executes one task or one parallel lane. Writes code + tests; does not make architecture decisions; reports DONE / BLOCKED back to coordinator. Default model is…
maid-plan-reviewer
MAID Phase 2 Quality Gate - Review manifest and tests before implementation.
test-coverage-analyzer
Use this agent to map changed code paths to test coverage, identify untested error paths, and review test quality. Rates each gap 1-10 for criticality. Context: A PR adds a new validation function with no tests. user: "Check test coverage" assistant: "I'll use the test-coverage-analyzer to map coverage and identify…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.